CN112765389A - Method and system for identifying high consequence area of oil and gas transmission pipeline and storage medium - Google Patents
Method and system for identifying high consequence area of oil and gas transmission pipeline and storage medium Download PDFInfo
- Publication number
- CN112765389A CN112765389A CN202110154927.0A CN202110154927A CN112765389A CN 112765389 A CN112765389 A CN 112765389A CN 202110154927 A CN202110154927 A CN 202110154927A CN 112765389 A CN112765389 A CN 112765389A
- Authority
- CN
- China
- Prior art keywords
- pipeline
- oil
- geographic
- image information
- identifying
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012549 training Methods 0.000 claims abstract description 21
- 235000013399 edible fruits Nutrition 0.000 claims abstract description 14
- 238000013528 artificial neural network Methods 0.000 claims abstract description 8
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 4
- 239000002360 explosive Substances 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 4
- 230000003321 amplification Effects 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 230000003190 augmentative effect Effects 0.000 claims 1
- 238000013145 classification model Methods 0.000 abstract description 3
- 238000003062 neural network model Methods 0.000 abstract description 2
- 238000011156 evaluation Methods 0.000 description 3
- 230000002093 peripheral effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/55—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Library & Information Science (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Remote Sensing (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method, a system and a storage medium for identifying a high consequence area of an oil and gas transmission pipeline, which are characterized in that by collecting geographic image information at two sides of the oil and gas transmission pipeline, identifying the collected geographic image information, adding a geographic attribute label, intercepting the geographic information image in the range of the influence radius of the high back fruit area at two sides of the central line of the pipeline to be identified according to the influence radius of the high back fruit area, the method comprises the steps of marking a geographic information image of a pipeline area to obtain a data training set, carrying out ResNet neural network model operation on the training set to obtain an image classification model, training a sample image data set through the ResNet neural network, carrying out automatic identification on geographic information of the oil and gas pipeline to be detected by using the obtained training model, and identifying a potential high posterior fruit area according to a geographic information label.
Description
Technical Field
The invention relates to the technical field of risk evaluation of oil and gas transmission pipelines, in particular to a method and a system for identifying a high consequence area of an oil and gas transmission pipeline and a storage medium.
Background
The high-consequence area of the oil and gas transmission pipeline refers to an area where the leakage of the pipeline can seriously endanger the public safety or cause great economic environmental loss, such as a personnel intensive place, an environment sensitive area, a flammable and explosive place and the like of a pipeline approach. The identification and management of the high-consequence area are important links of the integrity management of the pipeline and are also the basis of the risk evaluation and the integrity evaluation of the pipeline. The identification and management of the high-consequence areas of the pipeline are continuously carried out, and the identification method and the management measures are continuously standardized and refined in practice, so that the method has great significance for improving the management level of the integrity of the pipeline.
At present, manual exploration is a main means for identifying high-consequence areas of oil and gas pipelines. Specifically, technicians can manually patrol the periphery of the long oil and gas pipeline along the pipeline direction, segment the long oil and gas pipeline by taking the length of 2000 meters as a standard in patrol, and manually visually observe the environmental state of the periphery of each segment of the oil and gas pipeline within a certain range respectively so as to count the distribution conditions of personnel, buildings, water systems, vegetation, land, wetlands and roads in the periphery of each segment of the oil and gas pipeline within a certain range. And then estimating the number of personnel and buildings in the peripheral area of each section of oil and gas pipeline according to the statistical result of each section of oil and gas pipeline, and determining whether the peripheral area of each section of long oil and gas pipeline is a high back fruit area or not according to the number of personnel and buildings in the peripheral area of each section of oil and gas pipeline, thereby identifying the high back fruit area of the whole long oil and gas pipeline. The main problems in the prior art are that the long oil and gas pipeline is long, the surrounding environment of the pipeline is complex, and manual field inspection is often limited by geographical environment, climate environment and traffic, so that the workload for identifying high fruit areas is large, the working efficiency is low, the identification process is subjectively influenced, and the result is not accurate enough.
Disclosure of Invention
The invention aims to provide a method, a system and a storage medium for identifying a high-consequence area of an oil and gas transmission pipeline, so as to overcome the defects of the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for identifying a high consequence area of an oil and gas transmission pipeline comprises the following steps:
s1, collecting geographical image information on two sides of the oil and gas transmission pipeline, identifying the collected geographical image information, adding a geographical attribute label, and performing feature extraction on the geographical image information added with the geographical attribute label to form a sample image data set;
s2, constructing an identification network model, extracting the characteristics of the geographic image information added with the geographic attribute labels by using a ResNet neural network, and training the identification network model by using the extracted characteristics to obtain a classifier model;
and S3, automatically identifying the acquired pipeline image information to be analyzed with high consequence by using the classifier model.
Furthermore, the collected geographic image information on two sides of the oil and gas conveying pipeline takes the center line of the oil and gas pipeline to be detected as a symmetry axis and takes a set radius threshold value as a pipeline area with a symmetric radius; and setting the radius threshold not to exceed 2 times of the potential influence radius R of the pipeline, namely the acquisition range R of the geographic image information is less than 2R.
Further, for oil pipelines, the radius of potential impact is 200 meters;
r＝0.099√pd2formula (1)
In the formula, P, pipe conveying pressure and d pipe diameter;
the potential influence radius r of the pipeline is larger than the outer diameter of the oil and gas pipeline to be detected.
Further, the geographic attribute information added to the collected geographic image information on the two sides of the oil and gas transmission pipeline comprises information of buildings, flammable and explosive places, water sources, roads and villages.
Furthermore, geographic image information on two sides of the oil and gas transmission pipeline is manually identified, and geographic attribute labels are added.
Furthermore, geographic image information of the area where the oil and gas transmission pipeline is located is enlarged, and data volume is increased.
Further, the collected geographic image information is firstly randomly and horizontally turned over with the probability of 0.5, then the geographic image information is rotated between-10 degrees and 10 degrees with the probability of 0.75, then the geographic image information is randomly amplified by the probability of 0.75 between 1 and 1.05 times to form amplified geographic image information, then the amplified geographic image information is randomly and symmetrically distorted with the probability of 0.75 after the brightness of the amplified geographic image information is changed between 1 and 1.1 with the probability of 0.75, and the amplification of the geographic image information added with the geographic attribute label is completed.
Further, image data in potential influence ranges of two sides of the pipeline to be measured are obtained, a training model is adopted for prediction calculation, and a prediction threshold value is set to be 0.2.
A high consequence area recognition system of an oil and gas transmission pipeline based on a ResNet neural network comprises an acquisition module, a storage calculation module and a recognition module;
the acquisition module is used for acquiring an image of the pipeline to be analyzed, the image of the pipeline to be analyzed comprises a pipeline area which takes a central line of the pipeline to be analyzed as a symmetry axis and a set radius threshold as a symmetry radius, and the set radius threshold is larger than the outer diameter of the pipeline to be analyzed;
the storage calculation module is used for identifying a plurality of attribute categories in the pipeline image to be analyzed through an identification network model so as to determine the areas where the attribute categories are located, extracting the characteristics of the geographic image information added with the geographic attribute labels, and training the identification network model by using the extracted characteristics to obtain a classifier model;
and the identification module is used for identifying the high back fruit area of the pipeline to be analyzed from the pipeline areas in the plurality of image areas according to the ground feature attribute information of the areas where the plurality of attribute categories are located.
A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method of any one of claims 1 to 8.
Compared with the prior art, the invention has the following beneficial technical effects:
the invention discloses a method for identifying a high-consequence area of an oil and gas transmission pipeline, which comprises the steps of collecting geographic image information on two sides of the oil and gas transmission pipeline, identifying the collected geographic image information, adding a geographic attribute label, and carrying out feature extraction on the geographic image information added with the geographic attribute label to form a sample image data set; according to the influence radius of the high consequence region, intercepting the geographic information images in the influence radius range of the high back fruit region on two sides of the central line of the pipeline to be recognized, labeling the geographic information images in the pipeline region to obtain a data training set, performing ResNet neural network model operation on the training set to obtain an image classification model, predicting the central line image of the pipeline to be recognized by using the image classification model, and recognizing the potential high back fruit region; the method can train the sample image data set through the ResNet neural network, automatically identify the geographic information of the oil and gas pipeline to be detected by using the obtained training model, and identify the potential high posterior fruit zone according to the geographic information label.
A high consequence area identification system of an oil and gas transmission pipeline can acquire a target remote sensing image covering a pipeline area of a pipeline to be analyzed, automatically identify the target remote sensing image by adopting an image identification algorithm to determine the high consequence area of the target pipeline, and improve identification efficiency and accuracy compared with a method for manually identifying the high consequence area in the related art.
Drawings
Fig. 1 is a schematic diagram of a system structure according to an embodiment of the present invention.
FIG. 2 is a diagram illustrating a learning rate according to an embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the accompanying drawings:
a method for identifying a high consequence area of an oil and gas transmission pipeline comprises the following steps:
s1, collecting geographic image information on two sides of the oil and gas transmission pipeline, identifying the collected geographic image information, adding a geographic attribute label, and performing feature extraction on the geographic image information added with the geographic attribute label to form a sample image data set;
acquiring a geographic information image of a pipeline area to be identified according to the input pipeline path parameters; the geographic information images at two sides of the pipeline can directly extract recent satellite map information from open map software, and can also adopt geographic image information shot in the unmanned aerial vehicle line patrol process;
the collected geographic image information on two sides of the oil and gas conveying pipeline takes the center line of the oil and gas pipeline to be detected as a symmetry axis and takes a set radius threshold value as a pipeline area with a symmetric radius; and setting the radius threshold not to exceed 2 times of the potential influence radius R of the pipeline, namely the acquisition range R of the geographic image information is less than 2R. For the gas transmission pipeline, the potential influence radius of the pipeline is calculated by the formula (1); for oil pipelines, the radius of potential impact is 200 meters;
r＝0.099√pd2formula (1)
In the formula, P, pipe conveying pressure and d pipe diameter;
the potential influence radius r of the pipeline is larger than the outer diameter of the oil and gas pipeline to be detected.
Specifically, the geographic attribute information added to the collected geographic image information on two sides of the oil and gas transmission pipeline comprises building information, flammable and explosive places, water source information, highway information and village information; specifically, geographic image information on two sides of the oil and gas transmission pipeline can be manually identified, and geographic attribute labels are added;
s2, constructing an identification network model, extracting the characteristics of the geographic image information added with the geographic attribute labels by using a ResNet neural network, and training the identification network model by using the extracted characteristics to obtain a classifier model;
specifically, geographic image information of an area where the oil and gas transmission pipeline is located is enlarged, and data volume is increased; the method specifically comprises the following steps: firstly, randomly horizontally turning the collected geographic image information with the probability of 0.5, then rotating the collected geographic image information with the probability of 0.75 between-10 degrees and 10 degrees, then randomly amplifying the geographic image information with the probability of 0.75 between 1 and 1.05 times to form amplified geographic image information, then randomly symmetrically distorting the amplified geographic image information with the probability of 0.75 between 1 and 1.1 after changing the brightness, and completing the amplification of the geographic image information added with the geographic attribute label and increasing the data volume.
Dividing the sample images into a training set and a verification set, wherein specifically, 80% of the sample images are used as the training set, and 20% of the sample images are used as the verification set; the method comprises the steps of training by adopting a ResNet50 model with a learning rate of 1e-1 e-2 to obtain a training model, wherein the training model is obtained, the number of iterations of the recognition network model is not less than 5, and the obtained accuracy is as high as 95.8%.
And S3, automatically identifying the acquired pipeline image information to be analyzed with high consequence by using the classifier model.
Acquiring image data in potential influence ranges of two sides of a pipeline to be tested, and performing prediction calculation by adopting a training model, wherein a prediction threshold value is set to be 0.2 as shown in FIG. 2; in order to solve the multi-label problem, the prediction result is not unique, a threshold is adopted, and when the classification probability is greater than the threshold (here, 0.2), the label is set to be 1, otherwise, the label is set to be 0.
According to the geographical attribute labels, identifying high back fruit areas of the oil and gas pipeline to be detected from the pipeline areas of the pipeline image information to be analyzed, dividing the geographical image information of the oil and gas pipeline to be detected to obtain a plurality of image areas at intervals of the pipeline areas of the pipeline image information to be analyzed along the direction of the oil and gas pipeline to be detected and distance thresholds.
The method for identifying the high consequence area of the oil and gas pipeline to be detected from the pipeline areas in the plurality of image areas specifically comprises the following steps:
firstly, classifying the image information of the pipeline to be analyzed according to the geographic attribute label of the image information of the pipeline to be analyzed and the attribute category of the geographic attribute label; determining the region grade of the pipeline region in each image region in the plurality of image regions according to the ground feature attribute information of the region in which the attribute categories are located, wherein the region grade is used for indicating the population concentration degree of the pipeline region in each image region; and identifying a high back fruit area of the oil and gas pipeline to be detected from the pipeline areas in the plurality of image areas according to the ground feature attribute information of the areas where the plurality of attribute categories are located and the area grade of the pipeline area in each image area in the plurality of image areas.
A high consequence area recognition system of an oil and gas transmission pipeline based on a ResNet neural network comprises an acquisition module, wherein the acquisition module is used for acquiring an image of a pipeline to be analyzed, the image of the pipeline to be analyzed comprises a pipeline area which takes a central line of the pipeline to be analyzed as a symmetry axis and a set radius threshold as a symmetry radius, and the set radius threshold is larger than the outer diameter of the pipeline to be analyzed;
the storage calculation module is used for identifying a plurality of attribute categories in the pipeline image to be analyzed through an identification network model so as to determine the areas where the attribute categories are located, extracting the characteristics of the geographic image information added with the geographic attribute labels, and training the identification network model by using the extracted characteristics to obtain a classifier model;
and the identification module is used for identifying the high back fruit area of the pipeline to be analyzed from the pipeline areas in the plurality of image areas according to the ground feature attribute information of the areas where the plurality of attribute categories are located.
A high consequence area recognition device of an oil and gas transmission pipeline based on a ResNet neural network comprises a processor and a storage medium for storing executable instructions of the processor; the processor is configured to perform the method described above.
A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out a method for identifying a high consequence zone of an oil and gas transmission pipeline.
According to the method, the system and the storage medium for identifying the high consequence area of the oil and gas transmission pipeline, the complex relation between data is modeled by adopting a multi-layer representation through an identification network model, the distributed and layered feature representation can be learned by effectively utilizing a complex nonlinear function and a nonlinear composite function, so that the effective features of geographic information attributes on two sides of the pipeline are extracted, and the efficiency of identifying the high consequence area can be improved.
While the invention has been described in further detail in connection with specific embodiments and with the accompanying drawings, the description is not intended to limit the invention thereto, and it will be apparent to those skilled in the art that various changes and modifications can be made without departing from the invention.
Claims (10)
1. A method for identifying a high consequence area of an oil and gas transmission pipeline is characterized by comprising the following steps:
s1, collecting geographical image information on two sides of the oil and gas transmission pipeline, identifying the collected geographical image information, adding a geographical attribute label, and performing feature extraction on the geographical image information added with the geographical attribute label to form a sample image data set;
s2, constructing an identification network model, extracting the characteristics of the geographic image information added with the geographic attribute labels by using a ResNet neural network, and training the identification network model by using the extracted characteristics to obtain a classifier model;
and S3, automatically identifying the acquired pipeline image information to be analyzed with high consequence by using the classifier model.
2. The method for identifying the high consequence area of the oil and gas transmission pipeline according to claim 1, wherein the collected geographic image information on two sides of the oil and gas transmission pipeline takes the center line of the oil and gas pipeline to be detected as a symmetry axis and takes a set radius threshold value as a pipeline area with a symmetry radius; and setting the radius threshold not to exceed 2 times of the potential influence radius R of the pipeline, namely the acquisition range R of the geographic image information is less than 2R.
3. The method of claim 1, wherein for an oil and gas pipeline, the radius of potential impact is 200 meters;
in the formula, P, pipe conveying pressure and d pipe diameter;
the potential influence radius r of the pipeline is larger than the outer diameter of the oil and gas pipeline to be detected.
4. The method for identifying the high consequence area of the oil and gas transmission pipeline according to claim 1, wherein the geographical attribute information added to the geographical image information of the two sides of the collected oil and gas transmission pipeline comprises information of buildings, inflammable and explosive places, water sources, roads and villages.
5. The method for identifying the high consequence area of the oil and gas transmission pipeline according to claim 4, wherein the geographical attribute labels are added by manually identifying geographical image information on two sides of the oil and gas transmission pipeline.
6. The method for identifying the high consequence area of the oil and gas transmission pipeline according to claim 1, wherein the geographic image information of the area where the oil and gas transmission pipeline is located is augmented to increase the data volume.
7. The method for identifying the high-consequence area of the oil and gas transmission pipeline according to claim 6, wherein the acquired geographic image information is firstly randomly horizontally flipped with a probability of 0.5, then rotated between-10 and 10 degrees with a probability of 0.75, then randomly amplified with a probability of 0.75 between 1 and 1.05 times to form amplified geographic image information, and then randomly symmetrically distorted with a probability of 0.75 after the brightness of the amplified geographic image information is changed between 1 and 1.1 with a probability of 0.75, so that the amplification of the geographic image information added with the geographic attribute label is completed.
8. The method for identifying the high consequence area of the oil and gas transmission pipeline according to claim 6, wherein image data in potential influence ranges of two sides of the pipeline to be tested are obtained, a training model is adopted for prediction calculation, and a prediction threshold value is set to be 0.2.
9. A high consequence area identification system of an oil and gas transmission pipeline is characterized by comprising an acquisition module, a storage calculation module and an identification module;
the acquisition module is used for acquiring an image of the pipeline to be analyzed, the image of the pipeline to be analyzed comprises a pipeline area which takes a central line of the pipeline to be analyzed as a symmetry axis and a set radius threshold as a symmetry radius, and the set radius threshold is larger than the outer diameter of the pipeline to be analyzed;
the storage calculation module is used for identifying a plurality of attribute categories in the pipeline image to be analyzed through an identification network model so as to determine the areas where the attribute categories are located, extracting the characteristics of the geographic image information added with the geographic attribute labels, and training the identification network model by using the extracted characteristics to obtain a classifier model;
and the identification module is used for identifying the high back fruit area of the pipeline to be analyzed from the pipeline areas in the plurality of image areas according to the ground feature attribute information of the areas where the plurality of attribute categories are located.
10. A computer-readable storage medium, in which a computer program is stored, characterized in that the storage medium has a computer program stored therein, which, when being executed by a processor, carries out the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110154927.0A CN112765389A (en) | 2021-02-04 | 2021-02-04 | Method and system for identifying high consequence area of oil and gas transmission pipeline and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110154927.0A CN112765389A (en) | 2021-02-04 | 2021-02-04 | Method and system for identifying high consequence area of oil and gas transmission pipeline and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112765389A true CN112765389A (en) | 2021-05-07 |
Family
ID=75704944
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110154927.0A Pending CN112765389A (en) | 2021-02-04 | 2021-02-04 | Method and system for identifying high consequence area of oil and gas transmission pipeline and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112765389A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113688758A (en) * | 2021-08-31 | 2021-11-23 | 重庆科技学院 | Gas transmission pipeline high consequence district intelligent recognition system based on edge calculation |
| CN115170980A (en) * | 2022-07-06 | 2022-10-11 | 广东大鹏液化天然气有限公司 | Gas pipeline high consequence area intelligent identification method based on satellite image identification |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108960049A (en) * | 2018-05-25 | 2018-12-07 | 中国石油天然气股份有限公司 | Method and device for identifying high back fruit zone of long oil and gas pipeline and storage medium |
| CN110689051A (en) * | 2019-09-06 | 2020-01-14 | 北京市安全生产科学技术研究院 | Intelligent identification method for corrosion mode in gas pipeline based on transfer learning |
| CN110837941A (en) * | 2018-08-15 | 2020-02-25 | 中国石油天然气股份有限公司 | Method and device for risk prediction of oil and gas pipeline |
| CN111144498A (en) * | 2019-12-26 | 2020-05-12 | 深圳集智数字科技有限公司 | Image identification method and device |
| CN111614773A (en) * | 2020-05-26 | 2020-09-01 | 崔志诚 | Long-distance pipeline integrated management system and equipment |
| CN113688758A (en) * | 2021-08-31 | 2021-11-23 | 重庆科技学院 | Gas transmission pipeline high consequence district intelligent recognition system based on edge calculation |
-
2021
- 2021-02-04 CN CN202110154927.0A patent/CN112765389A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108960049A (en) * | 2018-05-25 | 2018-12-07 | 中国石油天然气股份有限公司 | Method and device for identifying high back fruit zone of long oil and gas pipeline and storage medium |
| CN110837941A (en) * | 2018-08-15 | 2020-02-25 | 中国石油天然气股份有限公司 | Method and device for risk prediction of oil and gas pipeline |
| CN110689051A (en) * | 2019-09-06 | 2020-01-14 | 北京市安全生产科学技术研究院 | Intelligent identification method for corrosion mode in gas pipeline based on transfer learning |
| CN111144498A (en) * | 2019-12-26 | 2020-05-12 | 深圳集智数字科技有限公司 | Image identification method and device |
| CN111614773A (en) * | 2020-05-26 | 2020-09-01 | 崔志诚 | Long-distance pipeline integrated management system and equipment |
| CN113688758A (en) * | 2021-08-31 | 2021-11-23 | 重庆科技学院 | Gas transmission pipeline high consequence district intelligent recognition system based on edge calculation |
Non-Patent Citations (1)
| Title |
|---|
| 李亚平: "基于BP神经网络的油气管道高后果区自动识别方法研究", 当代石油石化, vol. 27, no. 002, pages 38 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113688758A (en) * | 2021-08-31 | 2021-11-23 | 重庆科技学院 | Gas transmission pipeline high consequence district intelligent recognition system based on edge calculation |
| CN113688758B (en) * | 2021-08-31 | 2023-05-30 | 重庆科技学院 | Intelligent recognition system for high-consequence region of gas transmission pipeline based on edge calculation |
| CN115170980A (en) * | 2022-07-06 | 2022-10-11 | 广东大鹏液化天然气有限公司 | Gas pipeline high consequence area intelligent identification method based on satellite image identification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11933774B1 (en) | Leak detection event aggregation and ranking systems and methods | |
| US11222205B1 (en) | Systems and methods for hail damage verification on rooftops using computer vision and artificial intelligence | |
| US9599529B1 (en) | Systems and methods for likelihood-based mapping of areas surveyed for gas leaks using mobile survey equipment | |
| CN111797890A (en) | Method and system for detecting defects of power transmission line equipment | |
| CN114998852A (en) | Intelligent detection method for road pavement diseases based on deep learning | |
| CN105740642B (en) | MODIS fire satellite fire point accuracy method of discrimination based on multi- source Remote Sensing Data data | |
| CN112529012B (en) | Oil and gas pipeline inspection method, device, equipment and medium based on target matching | |
| CN112101159A (en) | Multi-temporal forest remote sensing image change monitoring method | |
| CN112765389A (en) | Method and system for identifying high consequence area of oil and gas transmission pipeline and storage medium | |
| US9159132B1 (en) | Process and system for identifying damage | |
| CN113531400B (en) | Pipeline line inspection method and system based on mobile equipment positioning data | |
| CN113255580A (en) | Method and device for identifying sprinkled objects and vehicle sprinkling and leaking | |
| CN112464920A (en) | FY-3D infrared hyperspectral cloud detection method based on extreme random tree | |
| CN116958907B (en) | Method and system for inspecting surrounding hidden danger targets of gas pipeline | |
| CN118413265B (en) | Satellite online state monitoring system and method | |
| CN117576073A (en) | Road defect detection method, device and medium based on improved YOLOv8 model | |
| CN118247662A (en) | Environment detection method for mining | |
| CN111238446B (en) | Communication tower inclination monitoring system | |
| Han et al. | Ceiling damage detection and safety assessment in large public buildings using semantic segmentation | |
| CN112966710A (en) | FY-3D infrared hyperspectral cloud detection method based on linear discriminant analysis | |
| CN117456342A (en) | Traffic accident risk assessment method and system based on street view image | |
| CN115272898A (en) | Pipe network unmanned aerial vehicle inspection video-based identification method, device, medium and equipment | |
| CN116433008A (en) | Database-based highway slope risk early warning method and system | |
| CN116205522A (en) | Landslide vulnerability evaluation method and system based on multidimensional CNN coupling | |
| CN115438547A (en) | Overall evaluation method and system based on pavement service state |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210507 |
|
| RJ01 | Rejection of invention patent application after publication |